菜单
Use for Claude Code reviews that need robotics, simulation, GPU-routing, sim-to-real, or BDD100K pipeline domain context.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when ingesting, validating, curating, or querying production sensor data as a versioned dataset-of-record, or wiring the dataset-ingest-curate workflow.
Use when generating adversarial scenarios via RL, ranking mined failures of a policy-under-test, or wiring the adversarial-scenario-hardening workflow.
Use when navigating the Cosmos3 integration in NPA or locating upstream Cosmos3 framework files, defaults, scripts, configs, recipes, and docs.
Use when Cosmos3 setup, fetch, inference, CUDA, uv, Docker, Hugging Face, GitHub, NGC, or checkpoint staging fails in NPA or in an upstream Cosmos framework checkout.
Use when setting up Cosmos3 access through NPA, checking source or Hugging Face reachability, staging the public Cosmos3 framework and checkpoint cache, or deciding which NPA workflow to use before inference.
Use when submitting, validating, or debugging NPA SkyPilot workflow YAMLs and workflow runner paths.
| name | physical-ai-context |
| description | Use for Claude Code reviews that need robotics, simulation, GPU-routing, sim-to-real, or BDD100K pipeline domain context. |
Sim-to-real pipeline:
Isaac Lab requires RT cores: L40S or RTX Pro 6000. H100 and H200 do not have RT cores.
Genesis serverless RL teacher training works. Visual demo generation is blocked on EGL/DRI device access in containers.
LeRobot is Tier 1 validated on B300. SONIC, GR00T, Isaac Lab, and Cosmos are vendor-paced on NVIDIA CUDA 13 alignment.
Route SONIC to H100; L40S on-demand capacity is effectively zero for the required preset.
The BDD100K demo pipeline is the reference end-to-end workflow. npa/src/npa/workflows/skypilot/bdd100k-pipeline.yaml is the canonical YAML.
Key claim: one YAML file describes a full Physical AI pipeline; SkyPilot orchestrates it on Nebius; results complete in about 30 minutes on a single H100.
